Make performance improvement to MIPS memcpy for small copies.

	* sysdeps/mips/memcpy.S (memcpy):  Add word copies for small aligned
	data.

diff --git a/ChangeLog b/ChangeLog
index cd2aa6841f121435b2c10159cb1bdd8f2a83597e..82f8fecaced4b78510ca972352fc13bb4f30c8d5 100644 (file)
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,8 @@
+2015-10-16  Steve Ellcey  <sellcey@imgtec.com>
+
+       * sysdeps/mips/memcpy.S (memcpy):  Add word copies for small aligned
+       data.
+
 2015-10-16  Joseph Myers  <joseph@codesourcery.com>
 
        * math/libm-test.inc (ceil_test_data): Add more tests and more

diff --git a/sysdeps/mips/memcpy.S b/sysdeps/mips/memcpy.S
index c85935b811912102d1892b57e37f51f7961e63cb..6f63405333e47e384af022bd102db6ceb5805ca3 100644 (file)
--- a/sysdeps/mips/memcpy.S
+++ b/sysdeps/mips/memcpy.S
@@ -295,7 +295,7 @@ L(memcpy):
  * size, copy dst pointer to v0 for the return value.
  */
        slti    t2,a2,(2 * NSIZE)
-       bne     t2,zero,L(lastb)
+       bne     t2,zero,L(lasts)
 #if defined(RETURN_FIRST_PREFETCH) || defined(RETURN_LAST_PREFETCH)
        move    v0,zero
 #else
@@ -546,7 +546,7 @@ L(chkw):
  */
 L(chk1w):
        andi    a2,t8,(NSIZE-1) /* a2 is the reminder past one (d)word chunks */
-       beq     a2,t8,L(lastb)
+       beq     a2,t8,L(lastw)
        PTR_SUBU a3,t8,a2       /* a3 is count of bytes in one (d)word chunks */
        PTR_ADDU a3,a0,a3       /* a3 is the dst address after loop */
 
@@ -558,6 +558,20 @@ L(wordCopy_loop):
        bne     a0,a3,L(wordCopy_loop)
        C_ST    REG3,UNIT(-1)(a0)
 
+/* If we have been copying double words, see if we can copy a single word
+   before doing byte copies.  We can have, at most, one word to copy.  */
+
+L(lastw):
+#ifdef USE_DOUBLE
+       andi    t8,a2,3         /* a2 is the remainder past 4 byte chunks.  */
+       beq     t8,a2,L(lastb)
+       lw      REG3,0(a1)
+       sw      REG3,0(a0)
+       PTR_ADDIU a0,a0,4
+       PTR_ADDIU a1,a1,4
+       move    a2,t8
+#endif
+
 /* Copy the last 8 (or 16) bytes */
 L(lastb):
        blez    a2,L(leave)
@@ -572,6 +586,33 @@ L(leave):
        j       ra
        nop
 
+/* We jump here with a memcpy of less than 8 or 16 bytes, depending on
+   whether or not USE_DOUBLE is defined.  Instead of just doing byte
+   copies, check the alignment and size and use lw/sw if possible.
+   Otherwise, do byte copies.  */
+
+L(lasts):
+       andi    t8,a2,3
+       beq     t8,a2,L(lastb)
+
+       andi    t9,a0,3
+       bne     t9,zero,L(lastb)
+       andi    t9,a1,3
+       bne     t9,zero,L(lastb)
+
+       PTR_SUBU a3,a2,t8
+       PTR_ADDU a3,a0,a3
+
+L(wcopy_loop):
+       lw      REG3,0(a1)
+       PTR_ADDIU a0,a0,4
+       PTR_ADDIU a1,a1,4
+       bne     a0,a3,L(wcopy_loop)
+       sw      REG3,-4(a0)
+
+       b       L(lastb)
+       move    a2,t8
+
 #ifndef R6_CODE
 /*
  * UNALIGNED case, got here with a3 = "negu a0"